What would we be without Google Maps reviews. Know the degree of general satisfaction of users with a restaurant, establishment of any kind, iconic place and others it helps us to be clearer if it is worth moving there or not. Of course, along the way, we can help companies to have more visibility or to make it clear that we did not like their service.
Google has explained how reviews work on Google Maps, so that we understand better what happens at the time of publicationsince there are important automatic learning mechanisms to moderate the millions of comments that end up being received throughout the year.
An AI pending what we publish
Google explains that the policy with reviews they are updating. They count as an interesting fact that, when the COVID-19 crisis arrived, they established in their content policy remove all review comments that encourage non-vaccination and criticism of establishments that followed sanitary criteria. Once this modification is done, algorithms analyze the review based on these new values.
Like almost everything at Google, machine learning is key. As soon as you post a review, it is sent to the moderation system. Given the high volume of reviews they receive every day, they use a combined system of machine learning algorithms, along with a human team to moderate.
The AI is capable of analyzing its content, review your account history, to find out if at any time you had any behavior that you consider suspicious. Come to value even the activity of your account, to know if you have done many reviews in a short timeif you have moved a lot on social networks or if you have tried to draw attention to your Google account to invite someone to vote en masse. In other words, they use a good part of the data they have about you.
If the system does not detect a violation of Google’s policy, the review is published automatically, in a matter of seconds. If you breach them, continue to analyze the content to end up publishing it or finally discarding it. The human team is in charge of review reported contenteither by SPAM, violence, discrimination and others.
More information | Google